Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds substantial behavioral context: it resolves drug names to all matching molecule forms (including salts and branded formulations), searches all of them simultaneously, and lists each molecule ID searched so empty results are interpretable. It also details the return fields and cites the data source (ChEMBL, EMBL-EBI). This goes well beyond the annotations and provides a clear picture of the tool's side-effect-free behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is detailed but every sentence carries weight: it starts with the core purpose, then gives query examples, explains the resolution behavior, lists return fields, and ends with clear usage guidance. It is well-structured, front-loaded, and avoids redundancy. The length is justified by the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even without an output schema, the description explicitly enumerates the returned data: action_type, mechanism_of_action, molecular target with ID and organism, molecule form, max clinical phase, curator comments, and PubMed references. It also covers how name resolution works and how to interpret results. This is complete context for an agent to predict the tool's output and behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and each parameter has an explanatory description; the description does not need to repeat them. It does add context about the resolution strategy (e.g., why the 'candidates' parameter matters) and the meaning of action_type, but this is marginal. Per the baseline for high schema coverage, a score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: 'Mechanism of action of a drug, from its NAME (or a ChEMBL molecule ID).' It includes concrete query examples like 'how does metformin work' and 'what does X inhibit,' making the tool's purpose unmistakable. This clearly distinguishes it from sibling tools like 'molecule' or 'target' by focusing on mechanism-of-action queries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: 'Reach for this for pharmacology, mode of action, drug-target identification, and any "how does this drug work" question.' It does not explicitly name alternatives or state when not to use the tool, but the context is strong enough to guide an agent. No exclusionary guidance is provided, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.